Reland "[llvm][llvm-objcopy] Added support for outputting to binary i…

…n llvm-objcopy"

This change adds the "-O binary" flag which directs llvm-objcopy to
output the object file to the same format as GNU objcopy does when given
the flag "-O binary". This was done by splitting the Object class into
two subclasses ObjectELF and ObjectBianry which each output a different
format but relay on the same code to read in the Object in Object.

Patch by Jake Ehrlich

Differential Revision: https://reviews.llvm.org/D34480

llvm-svn: 310018

llvm/test/tools/llvm-objcopy/basic-align-copy.test

@@ -0,0 +1,37 @@
+# RUN: yaml2obj %s -o %t
+# RUN: llvm-objcopy -O binary %t %t2
+# RUN: od -t x2 %t2 | FileCheck %s
+# RUN: wc -c < %t2 | FileCheck %s --check-prefix=SIZE
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    AddressAlign:    0x0000000000001000
+    Content:         "c3c3c3c3"
+  - Name:            .data
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    AddressAlign:    0x0000000000001000
+    Content:         "32"
+ProgramHeaders:
+  - Type: PT_LOAD
+    Flags: [ PF_X, PF_R ]
+    Sections:
+      - Section: .text
+  - Type: PT_LOAD
+    Flags: [ PF_R ]
+    Sections:
+      - Section: .data
+
+# CHECK:       0000000 c3c3 c3c3 0000 0000 0000 0000 0000 0000
+# CHECK-NEXT:  0000020 0000 0000 0000 0000 0000 0000 0000 0000
+# CHECK-NEXT:  *
+# CHECK-NEXT:  0010000 0032
+# SIZE:        4097

llvm/test/tools/llvm-objcopy/basic-binary-copy.test

@@ -0,0 +1,25 @@
+# RUN: yaml2obj %s -o %t
+# RUN: llvm-objcopy -O binary %t %t2
+# RUN: od -t x2 -v %t2 | FileCheck %s
+# RUN: wc -c < %t2 | FileCheck %s --check-prefix=SIZE
+
+!ELF
+FileHeader:
+  Class:           ELFCLASS64
+  Data:            ELFDATA2LSB
+  Type:            ET_EXEC
+  Machine:         EM_X86_64
+Sections:
+  - Name:            .text
+    Type:            SHT_PROGBITS
+    Flags:           [ SHF_ALLOC, SHF_EXECINSTR ]
+    AddressAlign:    0x0000000000001000
+    Content:         "c3c3c3c3"
+ProgramHeaders:
+  - Type: PT_LOAD
+    Flags: [ PF_X, PF_R ]
+    Sections:
+      - Section: .text
+
+# CHECK: 0000000 c3c3 c3c3
+# SIZE:  4

llvm/tools/llvm-objcopy/LLVMBuild.txt

@@ -18,4 +18,4 @@
 type = Tool
 name = llvm-objcopy
 parent = Tools
-required_libraries = Object MC
+required_libraries = Object Support MC

llvm/tools/llvm-objcopy/Object.cpp

@@ -42,6 +42,13 @@ void Segment::finalize() {
   }
 }
 
+void Segment::writeSegment(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart() + Offset;
+  // We want to maintain segments' interstitial data and contents exactly.
+  // This lets us just copy segments directly.
+  std::copy(std::begin(Contents), std::end(Contents), Buf);
+}
+
 void SectionBase::finalize() {}
 
 template <class ELFT>
@@ -99,7 +106,9 @@ template <class ELFT>
 void Object<ELFT>::readProgramHeaders(const ELFFile<ELFT> &ElfFile) {
   uint32_t Index = 0;
   for (const auto &Phdr : unwrapOrError(ElfFile.program_headers())) {
-    Segments.emplace_back(llvm::make_unique<Segment>());
+    ArrayRef<uint8_t> Data{ElfFile.base() + Phdr.p_offset,
+                           (size_t)Phdr.p_filesz};
+    Segments.emplace_back(llvm::make_unique<Segment>(Data));
     Segment &Seg = *Segments.back();
     Seg.Type = Phdr.p_type;
     Seg.Flags = Phdr.p_flags;
@@ -135,7 +144,7 @@ Object<ELFT>::makeSection(const llvm::object::ELFFile<ELFT> &ElfFile,
   default:
     Data = unwrapOrError(ElfFile.getSectionContents(&Shdr));
     return llvm::make_unique<Section>(Data);
-  };
+  }
 }
 
 template <class ELFT>
@@ -163,12 +172,6 @@ void Object<ELFT>::readSectionHeaders(const ELFFile<ELFT> &ElfFile) {
   }
 }
 
-template <class ELFT> size_t Object<ELFT>::totalSize() const {
-  // We already have the section header offset so we can calculate the total
-  // size by just adding up the size of each section header.
-  return SHOffset + Sections.size() * sizeof(Elf_Shdr) + sizeof(Elf_Shdr);
-}
-
 template <class ELFT> Object<ELFT>::Object(const ELFObjectFile<ELFT> &Obj) {
   const auto &ElfFile = *Obj.getELFFile();
   const auto &Ehdr = *ElfFile.getHeader();
@@ -187,22 +190,76 @@ template <class ELFT> Object<ELFT>::Object(const ELFObjectFile<ELFT> &Obj) {
       dyn_cast<StringTableSection>(Sections[Ehdr.e_shstrndx - 1].get());
 }
 
-template <class ELFT> void Object<ELFT>::sortSections() {
+template <class ELFT>
+void Object<ELFT>::writeHeader(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart();
+  Elf_Ehdr &Ehdr = *reinterpret_cast<Elf_Ehdr *>(Buf);
+  std::copy(Ident, Ident + 16, Ehdr.e_ident);
+  Ehdr.e_type = Type;
+  Ehdr.e_machine = Machine;
+  Ehdr.e_version = Version;
+  Ehdr.e_entry = Entry;
+  Ehdr.e_phoff = sizeof(Elf_Ehdr);
+  Ehdr.e_shoff = SHOffset;
+  Ehdr.e_flags = Flags;
+  Ehdr.e_ehsize = sizeof(Elf_Ehdr);
+  Ehdr.e_phentsize = sizeof(Elf_Phdr);
+  Ehdr.e_phnum = Segments.size();
+  Ehdr.e_shentsize = sizeof(Elf_Shdr);
+  Ehdr.e_shnum = Sections.size() + 1;
+  Ehdr.e_shstrndx = SectionNames->Index;
+}
+
+template <class ELFT>
+void Object<ELFT>::writeProgramHeaders(FileOutputBuffer &Out) const {
+  for (auto &Phdr : Segments)
+    Phdr->template writeHeader<ELFT>(Out);
+}
+
+template <class ELFT>
+void Object<ELFT>::writeSectionHeaders(FileOutputBuffer &Out) const {
+  uint8_t *Buf = Out.getBufferStart() + SHOffset;
+  // This reference serves to write the dummy section header at the begining
+  // of the file.
+  Elf_Shdr &Shdr = *reinterpret_cast<Elf_Shdr *>(Buf);
+  Shdr.sh_name = 0;
+  Shdr.sh_type = SHT_NULL;
+  Shdr.sh_flags = 0;
+  Shdr.sh_addr = 0;
+  Shdr.sh_offset = 0;
+  Shdr.sh_size = 0;
+  Shdr.sh_link = 0;
+  Shdr.sh_info = 0;
+  Shdr.sh_addralign = 0;
+  Shdr.sh_entsize = 0;
+
+  for (auto &Section : Sections)
+    Section->template writeHeader<ELFT>(Out);
+}
+
+template <class ELFT>
+void Object<ELFT>::writeSectionData(FileOutputBuffer &Out) const {
+  for (auto &Section : Sections)
+    Section->writeSection(Out);
+}
+
+template <class ELFT> void ELFObject<ELFT>::sortSections() {
   // Put all sections in offset order. Maintain the ordering as closely as
   // possible while meeting that demand however.
   auto CompareSections = [](const SecPtr &A, const SecPtr &B) {
     return A->OriginalOffset < B->OriginalOffset;
   };
-  std::stable_sort(std::begin(Sections), std::end(Sections), CompareSections);
+  std::stable_sort(std::begin(this->Sections), std::end(this->Sections),
+                   CompareSections);
 }
 
-template <class ELFT> void Object<ELFT>::assignOffsets() {
+template <class ELFT> void ELFObject<ELFT>::assignOffsets() {
   // Decide file offsets and indexes.
-  size_t PhdrSize = Segments.size() * sizeof(Elf_Phdr);
+  size_t PhdrSize = this->Segments.size() * sizeof(Elf_Phdr);
   // We can put section data after the ELF header and the program headers.
   uint64_t Offset = sizeof(Elf_Ehdr) + PhdrSize;
   uint64_t Index = 1;
-  for (auto &Section : Sections) {
+  for (auto &Section : this->Sections) {
     // The segment can have a different alignment than the section. In the case
     // that there is a parent segment then as long as we satisfy the alignment
     // of the segment it should follow that that the section is aligned.
@@ -249,93 +306,93 @@ template <class ELFT> void Object<ELFT>::assignOffsets() {
   // this needs to be 4-byte aligned and on 64-bit it needs to be 8-byte aligned
   // so the size of ELFT::Addr is used to ensure this.
   Offset = alignTo(Offset, sizeof(typename ELFT::Addr));
-  SHOffset = Offset;
+  this->SHOffset = Offset;
 }
 
-template <class ELFT> void Object<ELFT>::finalize() {
-  for (auto &Section : Sections)
-    SectionNames->addString(Section->Name);
+template <class ELFT> size_t ELFObject<ELFT>::totalSize() const {
+  // We already have the section header offset so we can calculate the total
+  // size by just adding up the size of each section header.
+  return this->SHOffset + this->Sections.size() * sizeof(Elf_Shdr) +
+         sizeof(Elf_Shdr);
+}
+
+template <class ELFT> void ELFObject<ELFT>::write(FileOutputBuffer &Out) const {
+  this->writeHeader(Out);
+  this->writeProgramHeaders(Out);
+  this->writeSectionData(Out);
+  this->writeSectionHeaders(Out);
+}
+
+template <class ELFT> void ELFObject<ELFT>::finalize() {
+  for (const auto &Section : this->Sections) {
+    this->SectionNames->addString(Section->Name);
+  }
 
   sortSections();
   assignOffsets();
 
   // Finalize SectionNames first so that we can assign name indexes.
-  SectionNames->finalize();
+  this->SectionNames->finalize();
   // Finally now that all offsets and indexes have been set we can finalize any
   // remaining issues.
-  uint64_t Offset = SHOffset + sizeof(Elf_Shdr);
-  for (auto &Section : Sections) {
+  uint64_t Offset = this->SHOffset + sizeof(Elf_Shdr);
+  for (auto &Section : this->Sections) {
     Section->HeaderOffset = Offset;
     Offset += sizeof(Elf_Shdr);
-    Section->NameIndex = SectionNames->findIndex(Section->Name);
+    Section->NameIndex = this->SectionNames->findIndex(Section->Name);
     Section->finalize();
   }
 
-  for (auto &Segment : Segments)
+  for (auto &Segment : this->Segments)
     Segment->finalize();
 }
 
-template <class ELFT>
-void Object<ELFT>::writeHeader(FileOutputBuffer &Out) const {
-  uint8_t *Buf = Out.getBufferStart();
-  Elf_Ehdr &Ehdr = *reinterpret_cast<Elf_Ehdr *>(Buf);
-  std::copy(Ident, Ident + 16, Ehdr.e_ident);
-  Ehdr.e_type = Type;
-  Ehdr.e_machine = Machine;
-  Ehdr.e_version = Version;
-  Ehdr.e_entry = Entry;
-  Ehdr.e_phoff = sizeof(Elf_Ehdr);
-  Ehdr.e_shoff = SHOffset;
-  Ehdr.e_flags = Flags;
-  Ehdr.e_ehsize = sizeof(Elf_Ehdr);
-  Ehdr.e_phentsize = sizeof(Elf_Phdr);
-  Ehdr.e_phnum = Segments.size();
-  Ehdr.e_shentsize = sizeof(Elf_Shdr);
-  Ehdr.e_shnum = Sections.size() + 1;
-  Ehdr.e_shstrndx = SectionNames->Index;
-}
-
-template <class ELFT>
-void Object<ELFT>::writeProgramHeaders(FileOutputBuffer &Out) const {
-  for (auto &Phdr : Segments)
-    Phdr->template writeHeader<ELFT>(Out);
+template <class ELFT> size_t BinaryObject<ELFT>::totalSize() const {
+  return TotalSize;
 }
 
 template <class ELFT>
-void Object<ELFT>::writeSectionHeaders(FileOutputBuffer &Out) const {
-  uint8_t *Buf = Out.getBufferStart() + SHOffset;
-  // This reference serves to write the dummy section header at the begining
-  // of the file.
-  Elf_Shdr &Shdr = *reinterpret_cast<Elf_Shdr *>(Buf);
-  Shdr.sh_name = 0;
-  Shdr.sh_type = SHT_NULL;
-  Shdr.sh_flags = 0;
-  Shdr.sh_addr = 0;
-  Shdr.sh_offset = 0;
-  Shdr.sh_size = 0;
-  Shdr.sh_link = 0;
-  Shdr.sh_info = 0;
-  Shdr.sh_addralign = 0;
-  Shdr.sh_entsize = 0;
-
-  for (auto &Section : Sections)
-    Section->template writeHeader<ELFT>(Out);
+void BinaryObject<ELFT>::write(FileOutputBuffer &Out) const {
+  for (auto &Segment : this->Segments) {
+    if (Segment->Type == llvm::ELF::PT_LOAD) {
+      Segment->writeSegment(Out);
+    }
+  }
 }
 
-template <class ELFT>
-void Object<ELFT>::writeSectionData(FileOutputBuffer &Out) const {
-  for (auto &Section : Sections)
-    Section->writeSection(Out);
-}
+template <class ELFT> void BinaryObject<ELFT>::finalize() {
+  for (auto &Segment : this->Segments)
+    Segment->finalize();
 
-template <class ELFT> void Object<ELFT>::write(FileOutputBuffer &Out) {
-  writeHeader(Out);
-  writeProgramHeaders(Out);
-  writeSectionData(Out);
-  writeSectionHeaders(Out);
+  // Put all segments in offset order.
+  auto CompareSegments = [](const SegPtr &A, const SegPtr &B) {
+    return A->Offset < B->Offset;
+  };
+  std::sort(std::begin(this->Segments), std::end(this->Segments),
+            CompareSegments);
+
+  uint64_t Offset = 0;
+  for (auto &Segment : this->Segments) {
+    if (Segment->Type == llvm::ELF::PT_LOAD) {
+      Offset = alignTo(Offset, Segment->Align);
+      Segment->Offset = Offset;
+      Offset += Segment->FileSize;
+    }
+  }
+  TotalSize = Offset;
 }
 
 template class Object<ELF64LE>;
 template class Object<ELF64BE>;
 template class Object<ELF32LE>;
 template class Object<ELF32BE>;
+
+template class ELFObject<ELF64LE>;
+template class ELFObject<ELF64BE>;
+template class ELFObject<ELF32LE>;
+template class ELFObject<ELF32BE>;
+
+template class BinaryObject<ELF64LE>;
+template class BinaryObject<ELF64BE>;
+template class BinaryObject<ELF32LE>;
+template class BinaryObject<ELF32BE>;